SRWToolkit: An Open Source Wizard of Oz Toolkit to Create Social Robotic Avatars

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nilgar, Atikkhan Faridkhan, Van Laerhoven, Kristof, Kinoti, Ayub
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912570332413952
author Nilgar, Atikkhan Faridkhan
Van Laerhoven, Kristof
Kinoti, Ayub
author_facet Nilgar, Atikkhan Faridkhan
Van Laerhoven, Kristof
Kinoti, Ayub
contents We present SRWToolkit, an open-source Wizard of Oz toolkit designed to facilitate the rapid prototyping of social robotic avatars powered by local large language models (LLMs). Our web-based toolkit enables multimodal interaction through text input, button-activated speech, and wake-word command. The toolkit offers real-time configuration of avatar appearance, behavior, language, and voice via an intuitive control panel. In contrast to prior works that rely on cloud-based LLM services, SRWToolkit emphasizes modularity and ensures on-device functionality through local LLM inference. In our small-scale user study ($n=11$), participants created and interacted with diverse robotic roles (hospital receptionist, mathematics teacher, and driving assistant), which demonstrated positive outcomes in the toolkit's usability, trust, and user experience. The toolkit enables rapid and efficient development of robot characters customized to researchers' needs, supporting scalable research in human-robot interaction.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04356
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SRWToolkit: An Open Source Wizard of Oz Toolkit to Create Social Robotic Avatars
Nilgar, Atikkhan Faridkhan
Van Laerhoven, Kristof
Kinoti, Ayub
Human-Computer Interaction
Robotics
We present SRWToolkit, an open-source Wizard of Oz toolkit designed to facilitate the rapid prototyping of social robotic avatars powered by local large language models (LLMs). Our web-based toolkit enables multimodal interaction through text input, button-activated speech, and wake-word command. The toolkit offers real-time configuration of avatar appearance, behavior, language, and voice via an intuitive control panel. In contrast to prior works that rely on cloud-based LLM services, SRWToolkit emphasizes modularity and ensures on-device functionality through local LLM inference. In our small-scale user study ($n=11$), participants created and interacted with diverse robotic roles (hospital receptionist, mathematics teacher, and driving assistant), which demonstrated positive outcomes in the toolkit's usability, trust, and user experience. The toolkit enables rapid and efficient development of robot characters customized to researchers' needs, supporting scalable research in human-robot interaction.
title SRWToolkit: An Open Source Wizard of Oz Toolkit to Create Social Robotic Avatars
topic Human-Computer Interaction
Robotics
url https://arxiv.org/abs/2509.04356